jira_add_attachment

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true. The description adds useful context beyond this: writes appear approval-gated ('approval_ref: Approved platform task UUID when resuming a write'), the effect parameter is a claim that Spring verifies, and routing is strictly governed. However, it does not clarify what the destructive behavior entails in Jira terms (e.g., replacing an existing attachment), so disclosure is partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-organized: operation identity first, then the routing constraint, then a tight parameter list. Every line earns its place given the 0% schema coverage. It is not padded, though it could arguably be slightly more front-loaded with a functional one-liner about attaching files before the governance details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The wrapper mechanics — governed routing, effect verification, idempotency, and approval-resume flow — are well covered, and an output schema exists so return values need no explanation. What is missing is the operative domain semantics: what the 'arguments' JSON should contain, what entity the attachment is added to, and what the destructive consequence is. An agent knows how the harness routes this call but not what payload to send.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description carries the full burden and compensates well by glossing all 7 parameters. It distinguishes similar identifiers ('project_id: Authenticated Project UUID' vs 'project_ref: Exact project correlation reference') and explains the effect/approval machinery. The 'arguments' gloss is thin, however — it says 'JSON string of arguments for the connector operation' without hinting at what the Jira operation expects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the tool as the Jira 'add_attachment' connector operation and gives its platform tool name, and the verb+resource in the name is specific. However, the text never states what the operation functionally does (e.g., attach a file to a Jira issue); 'Jira connector operation add_attachment' largely restates the name, and the remaining content is about routing/governance rather than the operation's effect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives such as jira_add_comment, xero_upload_attachment, or other Jira operations. The only contextual note, 'Routes only through the exact project/account governed connector authority,' is a routing constraint rather than usage direction. No conditions, exclusions, or alternative recommendations are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.